Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Sim] Skipped Multisim Values at 50k Iterations #1582

Open
graceful-coder opened this issue Sep 4, 2024 · 0 comments
Open

[Sim] Skipped Multisim Values at 50k Iterations #1582

graceful-coder opened this issue Sep 4, 2024 · 0 comments
Labels
Priority: Low Type: Bug Something isn't working

Comments

@graceful-coder
Copy link
Collaborator

graceful-coder commented Sep 4, 2024

Describe the bug

The ClassifLinearLasso & ClassifLinearElasticNet models are skipping over run_number = 0 the first multisim run at 50k iterations, regardless of their calibration. However, ClassifLinearLasso_Balanced & ClassifLinearElasticNet_Balanced models are unaffected.

When my_ppss.yaml params are set to:

multisim_ss:
  approach: SimpleSweep # SimpleSweep | FastSweep (future) | ..
  sweep_params:
  - trader_ss.buy_amt: 1000 USD
  - predictoor_ss.aimodel_data_ss.max_n_train: 1000, 2000, 5000
  - predictoor_ss.aimodel_data_ss.autoregressive_n: 1, 2

The models are skipping over the first multisim run with max_n_train = 1000 and autoregressive_n = 1 but complete the rest of the multisim flow. This issue is reproduced in simulations with all three calibrations (Sigmoid, Isotonic, and None) at 50k iterations. However, this issue is not occurring at 5k iterations.

To Reproduce

  1. Attached is the my_ppss.yaml file which failed
  2. Run the pdr multisim with the attached my_ppss.yaml file
    my_ppss_yaml.txt
@graceful-coder graceful-coder added Type: Bug Something isn't working Priority: Low labels Sep 4, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Priority: Low Type: Bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant